Papers › Domain-aware Triplet loss in Domain Generalization

Domain-aware Triplet loss in Domain Generalization

1 Mar 2023arXiv:2303.01233archive 2025-07-28

Kaiyu Guo, Brian Lovell

Despite much progress being made in the field of object recognition with the advances of deep learning, there are still several factors negatively affecting the performance of deep learning models. Domain shift is one of these factors and is caused by discrepancies in the distributions of the testing and training data. In this paper, we focus on the problem of compact feature clustering in domain generalization to help optimize the embedding space from multi-domain data. We design a domainaware triplet loss for domain generalization to help the model to not only cluster similar semantic features, but also to disperse features arising from the domain. Unlike previous methods focusing on distribution alignment, our algorithm is designed to disperse domain information in the embedding space. The basic idea is motivated based on the assumption that embedding features can be clustered based on domain information, which is mathematically and empirically supported in this paper. In addition, during our exploration of feature clustering in domain generalization, we note that factors affecting the convergence of metric learning loss in domain generalization are more important than the pre-defined domains. To solve this issue, we utilize two methods to normalize the embedding space, reducing the internal covariate shift of the embedding features. The ablation study demonstrates the effectiveness of our algorithm. Moreover, the experiments on the benchmark datasets, including PACS, VLCS and Office-Home, show that our method outperforms related methods focusing on domain discrepancy. In particular, our results on RegnetY-16 are significantly better than state-of-the-art methods on the benchmark datasets. Our code will be released at https://github.com/workerbcd/DCT

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 12 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 1 repository, 9 ran (7 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 9 samples that ran has no recorded date.

workerbcd/dct officialmentioned in paperpytorchMITSyntology: 12 samples, 9 ran (2 instrument-failed) · 3 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

12 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
2ran · our draft was wrong
4ran
3unverified

Licence: 1 of the 12 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from workerbcd/dct. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

workerbcd/dct official repository 12 samples, 9 ran (2 instrument-failed) · 3 unverified
build_blocks in 5 papers domainbed/backbones/new_networks.py ran MIT (permissive) · 83e280af851073dd · report fixture: signature model:callable/0/?, block_name_dict:dict/0/? · returned list · level recorded 2026-09-25
get_module in 37 papers domainbed/backbones/new_networks.py ran MIT (permissive) · c8980fa1301b0ca7 · report fixture: signature module:callable/0/?, name:str/0/str · returned SimpleBlock · level recorded 2026-09-24
hashable in 21 papers domainbed/lib/query.py ran · honoured contract fingerprinted MIT (permissive) · 71a3a61ceed99bf3 · report fixture: signature obj:int/0/int · returned int · level recorded 2026-09-24
levelize in 7 papers domainbed/lib/logger.py ran · honoured contract fingerprinted MIT (permissive) · 2f597a2077a1c95d · report fixture: signature levelname:str/0/str · returned int · level recorded 2026-09-24
make_selector_fn in 21 papers domainbed/lib/query.py ran · our draft was wrong MIT (permissive) · 2f8af5779e1edcb6 · report fixture: signature selector:str/0/str · returned function · level recorded 2026-09-24
make_weights_for_balanced_classes in 23 papers domainbed/lib/misc.py ran MIT (permissive) · 86798fbb2fc042f5 · report fixture: signature dataset:list/1/dict · returned Tensor · level recorded 2026-09-25
random_pairs_of_minibatches in 9 papers domainbed/lib/misc.py ran · our draft was wrong MIT (permissive) · 4fa2b54178fcc1df · report fixture: signature minibatches:list/1/tuple · returned list · level recorded 2026-09-22
to_minibatch in 8 papers domainbed/algorithms/algorithms.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 12c23ce22097acd0 · report fixture: signature x:list/1/Tensor, y:list/1/Tensor · returned list · level recorded, date not recorded
to_row in 6 papers domainbed/lib/misc.py ran MIT (permissive) · 5dd6a674fbe45a89 · report fixture: signature row:list/1/float, colwidth:int/0/int, latex:bool/0/bool · returned str · level recorded 2026-09-24
accuracy_from_loader in 7 papers domainbed/evaluator.py unverified MIT (permissive) · 0ca4d46da891e3df · report
default_hparams in 10 papers domainbed/hparams_registry.py unverified MIT (permissive) · 480b953f8f91b3b1 · report
random_hparams in 8 papers domainbed/hparams_registry.py unverified MIT (permissive) · dbeb3657dc35373d · report

Tasks

ClusteringDomain GeneralizationMetric LearningObject Recognition

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Generalization Office-Home D-Triplet(RegNetY-16GF) Average Accuracy 82.6 #13 of 45 Archive leaderboard report
Domain Generalization Office-Home D-Triplet(Resnet-50) Average Accuracy 70.3 #32 of 45 Archive leaderboard report
Domain Generalization PACS D-Triplet(RegNetY-16GF) Average Accuracy 97.6 #4 of 133 Archive leaderboard report
Domain Generalization PACS D-Triplet(Resnet-50) Average Accuracy 87.3 #39 of 133 Archive leaderboard report
Domain Generalization VLCS D-Triplet(RegNetY-16GF) Average Accuracy 82.9 #6 of 37 Archive leaderboard report
Domain Generalization VLCS D-Triplet(Resnet-50) Average Accuracy 79.3 #26 of 37 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Triplet Loss

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections